INDEX

Explanations

instances of the word "Amherst" and its variations

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

idot

-0.18

Ã©ru

-0.15

itu

-0.15

.gdx

-0.15

rients

-0.15

gings

-0.14

.operator

-0.14

uctive

-0.14

Ħĸ

-0.14

pressor

-0.14

POSITIVE LOGITS

Am

0.23

am

0.19

Am

0.18

enburg

0.18

islav

0.17

uisse

0.16

åģ¥

0.15

 Lawson

0.15

(am

0.15

aÄĩ

0.15

Activations Density 0.028%

instances of the word "Amherst" and its variations

No Comments

No Known Activations